Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint, which cover safety. The description adds the key behavioral detail of randomness ('at random') and the scope ('from the archive'), which is not present in annotations. No contradiction exists, and the added context is useful.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence is crisp and functional. The second sentence is a poetic metaphor that is non-essential but adds a hint of intent. It is not wasteful enough to lower the score significantly, but it could be omitted for tighter structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the absence of parameters and output schema, the description covers the core behavior: random selection from the archive. It does not specify the return format, but for a simple random picker this is acceptable. The context from sibling tools reinforces its niche.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, so schema coverage is 100% by default. The description provides no parameter details, but none are needed. The baseline of 4 applies because the tool is parameterless and the description clearly conveys the selection mechanism.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action: 'One project chosen at random from the archive.' This clearly distinguishes the tool from siblings like get_project (targeted lookup) and search (query-based), which require parameters. The verb 'chosen' and resource 'project from the archive' are explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for serendipitous discovery ('Editorial serendipity') but never explicitly states when to use this tool versus alternatives, nor does it exclude scenarios like needing a specific project. The guidance is implied rather than spelled out.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.